Our engineering and design team has been testing 20+ side-by-side comparisons across frontier and open models. All runs are public and open source. Benchmark for this demo here:
github.com/CommandCode... Tested Kimi K3 to build a 3D portfolio website.
- Used the /design command.
- Built in 3 prompts: build, continue, then recolor
- Full session cost: $0.57
The interesting part: Recolor replaced and added an entirely new palette with the same layout and animations in seconds. 
Our engineering and design team has been testing 20+ side-by-side comparisons across frontier and open models. All runs are public and open source. Benchmark for this demo here:
github.com/CommandCode... We tested Kimi K3 to build liquid metal text that wraps with your cursor in Three[.]js
- Used the /design command
- 3 prompts to get this effect
- Full session cost: $0.77
Open models deliver their best when used with the right harness. 
You can create custom agents for yourself or for your team.
Run /agents, describe what it should do, which tools it can access, and Command Code handles the rest.
Commit it to your repo and your team can use them too.
Share what agents have you built with the Command Code CLI. 
feeling of relief when the phone alarm is a emergency weather alert instead of pagerduty
use a better harness to get the best open models performance, and to save time and money. read this why ↓
x.com/MrAhmadAwai... update: today Command Code overtook Claude Code on OpenRouter.
devs are picking the harness built for open models over monkey-patching proxy hacks into claude code. it has sub par perf & wastes your time/money with open models as it's only meant for claude models.
x.com/MrAhmadAwai... 
Grok is this real?
Changelog #0299
• Railway plugin for Grok Build
• Manage CDN caching in the CLI
• Fixes and improvements
railway.com/changelog/20... "the pelicans are still all rubbish" @simonwillison.net 
Here's the benchmark:
github.com/CommandCode... We compare Kimi K3 with Fable 5.
We use our /design command for this test.
The result is insanely good for only $0.035. The section and scroll animations, plus the mouse-hover animation in the footer, are outstanding.
What you’re cooking with /design using Kimi K3? 
Over the past year, Orion Pharma, a leader in human and veterinary medicines, has gone deep with Elicit. Serhii Vakal, PhD, Lead ML/AI Scientist at Orion Pharma, shared a compelling story about how he used Elicit.
Read the full case study: elicit.com/customer-st... 
docs.netlify.com just scored 97/100 (A) on both Fern's and Mintlify's agent-readiness audits. Append .md to any docs URL and see for yourself! Clean markdown, no boilerplate.
Agents deserve nice docs too.
buildwithfern.com/agent-score/... 
See what migration history looks like in Studio and try it yourself:
pris.ly/prisma-stud... Prisma Next (soon Prisma 8) now lets you inspect a database’s applied migration history in Prisma Studio, with the schema changes and exact SQL that ran. 
Here's the benchmark:
github.com/CommandCode... Kimi K3 vs GPT-5.6 Sol vs Fable 5
Same /design prompt across all three.
Kimi K3 nailed the design and pace. Fable 5 & GPT-5.6 Sol both play too fast (not sped up).
Ranking & cost:
→ Kimi K3: 9.5 · $0.030
→ Fable 5: 7.5 · $0.38
→ GPT-5.6 Sol: 7 · $0.11 
In our latest fireside chat, Sheila Leunig, General Counsel at Elicit, and Zen Jelenje, Founder of Nascent Studio and former Data Solutions Lead at Elsevier, discussed how researchers can navigate copyright and data rights as AI becomes a larger part of research.
Recording: youtu.be/6kQPwhjjhJ4 
new video from Jilles just dropped! thank you for featuring Atuin <3
www.youtube.com/watch?v=JzVX... oh man, one of my articles got onto hacker news and i have a new tagline for the blog!
Comparing Fable vs GPT 5.6 outputs shouldn't require two provider accounts and two bills. On Netlify it's one account, switch models whenever.
The new Pro tiers = more credits to burn on exactly this kind of experimenting.
www.netlify.com/blog/new-pro...